How to use this Blog?

Posted on November 16, 2015 by drtamil@gmail.com

This blog is to complement my lectures on medical statistics for both undergraduate (FF2613) and postgraduate (FK6163) in Faculty of Medicine, Universiti Kebangsaan Malaysia.

So if you are a medical undergraduate, looking for notes and practicals on medical statistics, to start, please click on the FF2613 button as illustrated below.

clickff2613

So if you are a medical postgraduate, looking for notes and practicals on medical statistics, to start, please click on the FK6163 button as illustrated below.

clickfk6163

So if you are a medical researcher, looking for notes and tools for sample size calculation, to start, please click on the “Sample Size” button as illustrated below.

clicksamplesize

Some of the “Download” medical statistics notes pages are protected by password. The passwords are available from your respective Facebook group page. For FF2613, the passwords are shared HERE. For FK6163, the passwords are shared HERE. For FK6193, the passwords are shared HERE

If you want to be able to read the notes only, they are also available from SlideShare.

Posted in Web2.0 | Leave a comment

FK6193 – CBE – Rasch Dichotomous

Posted on July 7, 2022 by drtamil@gmail.com

Welcome to the first ever examination on Rasch Dichotomous analysis in UKM Faculty of Medicine. Please make sure that you have installed Bond and Fox Steps or Winsteps prior to doing this assignment.

Use your browser to download your Rasch data for this assignment from the following link;

Do the following analysis on the data using “Bond and Fox Steps” or Winsteps then submit your answers via the LINK emailed to you before 10.30am 7th July 2022.

Scenario: Every semester, the ability of postgrad students on statistics are assessed using 30 OBA questions. To ensure the questions are reliable and able to discriminate good from poor students, reliability analysis are conducted on it regularly.

  1. Open the given data using BNFSteps/WinSteps and press Enter twice. Let it generate the Fit Statistics. Look at the Infit results for both Person and Item. Is it acceptable? Copy and paste the table into your Word file.
  2. Click on Plots>Bubble Plot. Select type “Infit” and display marker by “Label”. Interpret the results. Copy and paste the plot into your Word file.
  3. Generate the Wright Map (Variable Maps). Zoom out so the entire map fits your screen, printscreen and paste the image into your Word file. Interpret the results accordingly. Answer the questions given in the Google Form.
  4. Generate the Person Measures table (Table 17). Confirm your earlier answers of most able and least able students. Zoom out so the entire table fits your screen, printscreen and paste the image into your Word file. Are there any Infit ZSTD values larger than 2.0? Remember that ZSTD for Infit is supposed to be 0.
  5. Generate the Item Measures table (Table 13). Zoom out so the entire table fits your screen, printscreen and paste the image into your Word file. Are there any Infit ZSTD values larger than 2.0? Remember that ZSTD for Infit is supposed to be 0. Look at the point measure correlation, which questions were unable to discriminate good from poor students (r<0.32).
  6. Generate the Summary Statistics for All Persons & Items. Zoom out so the entire table fits your screen, printscreen and paste the image into your Word file. Determine the following;
    • Determine the KR-20 reliability index of the questions.
    • Compare the mean logit of Person Ability and Item Difficulty. Calculate the P(theta). The questions are Easy or Difficult for this group of students?
    • The students can be divided into how many groups? Show the calculation.

Upload your Word file into the Google Form, using your matric number (i.e. P20627) as it’s filename.

Just in case your answers go missing in the ethers of cyberspace, please email the above Word document file (e.g. P20627.doc) to statsexam@gmail.com, using your matric number (i.e. P20627) as its’ subject header.

Deadline 10.30 am 7th July 2022. After that time, no more submissions will be accepted.

Posted in Assignment, FK6193 | Leave a comment

FK6193 Introduction to Stata

Posted on June 16, 2022 by drtamil@gmail.com

Click HERE to view and download Powerpoint notes.

Click HERE to download dataset.

Posted in Uncategorized | Leave a comment

FF3618/FK6163 – Computer Based Examination on Analysis Using SPSS

Posted on March 29, 2022 by drtamil@gmail.com

Use your browser to download your SPSS data based on your matric number from the following link;

Click HERE and save it on your Desktop.

Either right-click on the downloaded file and select SPSS, or open SPSS, then click open file, then select the downloaded file.

Then do the following analysis on the data using SPSS then submit your answers via the LINK sent earlier to your email.

A study to identify factors that can cause small for gestational age (SGA) was conducted. Among the factors studied were the mothers’ body mass index (BMI). It is believed that mothers with lower BMI were of higher risk to get SGA babies.

1. Create a new variable mBMI (Mothers’ Body Mass Index) from the mothers’ HEIGHT (in metre) & WEIGHT (first trimester weight in kg). mBMI = weight in kg/(height in metre)2. Calculate the following for mBMI;

  • Mean
  • Standard deviation

2. Create a new variable OBESCLAS (Classification of Obesity) from mBMI. Use the following cutoff point;

  • <20 = Underweight
  • 20 – 24.99 = Normal
  • 25 or larger = Overweight

Create a frequency table for OBESCLAS.

3. Conduct the appropriate statistical test to test whether there is any association between OBESCLAS (Underweight/Normal/Overweight) and OUTCOME.

4. Conduct the appropriate statistical test to test whether there is any association between BMI and OUTCOME.

5. Conduct the appropriate statistical test to find any association between OBESCLAS (Underweight/Normal/Overweight) and BIRTHWGT.

6. Assuming that both variables mBMI & BIRTHWGT are normally distributed,

  • conduct an appropriate statistical test to prove the association between the two variables.
  • Demonstrate the association using the appropriate chart. Determine the coefficient of determination.

7. Conduct Simple Linear Regression using BIRTHWGT as the dependent variable. Try to come out with a formula that will predict the baby’s birth weight based on the mother’s BMI.

y = a + bx

Save your SPSS sav data file as a new SPSS file and save it somewhere safe as evidence/backup, in case of issues later.

Upon finishing, please click the SUBMIT button to submit your answers.

Posted in FK6163(E), Minitest, SPSS | Tagged , | Leave a comment

Presentation Year 2 2021/2022

Posted on December 23, 2021 by drtamil@gmail.com

Lab 1

Lab 2

Lab 3

Lab 4

Lab 5

Lab 6

Lab 7

Lab 8

Posted in Uncategorized | Leave a comment

FFFK6193 – Computer Based Examination on Analysis Using R Studio

Posted on July 1, 2021 by drtamil@gmail.com

Use your browser to download your Rdata based on your matric number from the following link;

Click HERE

Either right-click on the downloaded file and select RStudio, or open RStudio, then click open file, then select the downloaded file.

Then do the following analysis on the data using R Studio then submit your answers via this LINK.

A study to identify factors that can cause small for gestational age (SGA) was conducted. Among the factors studied were the mothers’ body mass index (BMI). It is believed that mothers with lower BMI were of higher risk to get SGA babies.

1. Create a new variable mBMI (Mothers’ Body Mass Index) from the mothers’ HEIGHT (in metre) & WEIGHT (first trimester weight in kg). mBMI = weight in kg/(height in metre)2. Calculate the following for mBMI;

  • Mean
  • Standard deviation

Copy and paste your answers into your Word file.

2. Create a new variable OBESCLAS (Classification of Obesity) from mBMI. Use the following cutoff point;

  • <20 = Underweight
  • 20 – 24.99 = Normal
  • 25 or larger = Overweight

Create a frequency table for OBESCLAS. Copy and paste the table into your Word file.

3. Conduct the appropriate statistical test to test whether there is any association between OBESCLAS (Underweight/Normal/Overweight) and OUTCOME.

Copy and paste the appropriate tables along with the interpretation into your Word file.

4. Conduct the appropriate statistical test to test whether there is any association between BMI and OUTCOME.

Copy and paste the appropriate tables along with the interpretation into your Word file.

5. Conduct the appropriate statistical test to find any association between OBESCLAS (Underweight/Normal/Overweight) and BIRTHWGT.

Copy and paste the appropriate tables along with the interpretation into your Word file.

6. Assuming that both variables mBMI & BIRTHWGT are normally distributed,

  • conduct an appropriate statistical test to prove the association between the two variables.
  • Demonstrate the association using the appropriate chart. Determine the coefficient of determination.

Copy and paste the above charts and your answers into your Word file.

7. Conduct Simple Linear Regression using BIRTHWGT as the dependent variable. Try to come out with a formula that will predict the baby’s birth weight based on the mother’s BMI.

y = a + bx

Copy and paste the appropriate tables and supporting chart along with the interpretation into your Word file.

Save it all as a new RData file and save it somewhere safe as evidence/backup, in case of issues later.

Copy all the text (select with mouse, then Ctrl-C) in the Console window and paste (Ctrl-V) into your Word file.
Save your Word file using your matric number as its filename i.e. P999999.doc. Keep it safe. Upon finishing, please click the SUBMIT button to submit your answers.

Just in case your answers go missing in the ether of cyberspace, please keep your Word file safe.

Posted in FK6193, Minitest, R | Tagged , | Leave a comment

FK6193 GLM Repeated Measures

Posted on December 30, 2020 by drtamil@gmail.com
  1. YH Chan’s 301 article
  2. YH Chan’s 301a article
  3. Lecture Notes based on YH Chan’s article
  4. Data SPSS

Posted in Uncategorized | Leave a comment

CL12 Cox Regression FK6193

Posted on December 27, 2020 by drtamil@gmail.com

Posted in FK6193 | Leave a comment

Multiple Linear Regression

Posted on December 21, 2020 by drtamil@gmail.com
L4 Multiple Linear RegressionDownload
SPSS fileDownload
Posted in FK6193 | Leave a comment

Multiple “Logit”-stic Regression

Posted on December 16, 2020 by drtamil@gmail.com

Notes
Data
Excel spreadsheet
Origin of Logistic Regression
Manual Calculation of SLogR

logisticDownload
Posted in FK6193, Lectures | Leave a comment

Project Presentation Year 2 2020/2021

Posted on December 8, 2020 by drtamil@gmail.com

Lab 1

Lab 1

Lab 2

Lab 2

Lab 3

Lab 3

Lab 4

Lab 5

Lab 5

Lab 6

Lab 6

Lab 7

Lab 7

Lab 8

Lab 9

Lab 9

Lab 10

Lab 10
Posted in FF2613 | Leave a comment